{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6FFVUCVUUJL52TEA2P45SWYX7V","short_pith_number":"pith:6FFVUCVU","schema_version":"1.0","canonical_sha256":"f14b5a0ab4a257dd4c80d3f9d95b17fd5b8ee01abfbdb50c52c0299122fbdeaf","source":{"kind":"arxiv","id":"2205.11370","version":2},"attestation_state":"computed","paper":{"title":"Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Gow-Smith, Jade Scott, Mark McConville, Roibeard \\'O Maolalaigh, William Gillies","submitted_at":"2022-05-23T15:04:26Z","abstract_excerpt":"The Book of the Dean of Lismore (BDL) is a 16th-century Scottish Gaelic manuscript written in a non-standard orthography. In this work, we outline the problem of transliterating the text of the BDL into a standardised orthography, and perform exploratory experiments using Transformer-based models for this task. In particular, we focus on the task of word-level transliteration, and achieve a character-level BLEU score of 54.15 with our best model, a BART architecture pre-trained on the text of Scottish Gaelic Wikipedia and then fine-tuned on around 2,000 word-level parallel examples. Our initia"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.11370","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T15:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"963c4b79098c30a4078c18f07d28138281b77487471d02d92936abcd54d06575","abstract_canon_sha256":"7be9cea1b92eae137d7dc4d73d40f4bd2779d96dc892e38552054ad21d236753"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:00.687633Z","signature_b64":"QNq50PlpxbzM+MX5bKuuSk0bawIrgrMGU5XWGj+v5VwExlEbtDc+0A6Er5k0Sm2Mu+uleb6s09uyOhC5dPGPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f14b5a0ab4a257dd4c80d3f9d95b17fd5b8ee01abfbdb50c52c0299122fbdeaf","last_reissued_at":"2026-07-05T04:28:00.687192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:00.687192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Gow-Smith, Jade Scott, Mark McConville, Roibeard \\'O Maolalaigh, William Gillies","submitted_at":"2022-05-23T15:04:26Z","abstract_excerpt":"The Book of the Dean of Lismore (BDL) is a 16th-century Scottish Gaelic manuscript written in a non-standard orthography. In this work, we outline the problem of transliterating the text of the BDL into a standardised orthography, and perform exploratory experiments using Transformer-based models for this task. In particular, we focus on the task of word-level transliteration, and achieve a character-level BLEU score of 54.15 with our best model, a BART architecture pre-trained on the text of Scottish Gaelic Wikipedia and then fine-tuned on around 2,000 word-level parallel examples. Our initia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11370","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.11370/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.11370","created_at":"2026-07-05T04:28:00.687255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11370v2","created_at":"2026-07-05T04:28:00.687255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11370","created_at":"2026-07-05T04:28:00.687255+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FFVUCVUUJL5","created_at":"2026-07-05T04:28:00.687255+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FFVUCVUUJL52TEA","created_at":"2026-07-05T04:28:00.687255+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FFVUCVU","created_at":"2026-07-05T04:28:00.687255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V","json":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V.json","graph_json":"https://pith.science/api/pith-number/6FFVUCVUUJL52TEA2P45SWYX7V/graph.json","events_json":"https://pith.science/api/pith-number/6FFVUCVUUJL52TEA2P45SWYX7V/events.json","paper":"https://pith.science/paper/6FFVUCVU"},"agent_actions":{"view_html":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V","download_json":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V.json","view_paper":"https://pith.science/paper/6FFVUCVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11370&json=true","fetch_graph":"https://pith.science/api/pith-number/6FFVUCVUUJL52TEA2P45SWYX7V/graph.json","fetch_events":"https://pith.science/api/pith-number/6FFVUCVUUJL52TEA2P45SWYX7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V/action/storage_attestation","attest_author":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V/action/author_attestation","sign_citation":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V/action/citation_signature","submit_replication":"https://pith.science/pith/6FFVUCVUUJL52TEA2P45SWYX7V/action/replication_record"}},"created_at":"2026-07-05T04:28:00.687255+00:00","updated_at":"2026-07-05T04:28:00.687255+00:00"}